Description:

The Get Text from Image step enables a FlowWright workflow to extract text from an image using Azure Cognitive Services.

The step belongs to the Azure Cognitive Services category and is exposed in FlowWright with the display name Get Text from Image. Its XML definition describes its capability as “Extract text from an image.”

The step accepts an image file path and can optionally use a selected image region when extracting the text. It stores the extracted text and a percentage result in the configured workflow variables or global variables.

This allows image-based text extraction to become part of an automated workflow. For example, a workflow can process scanned images, photographs, labels, or other image content and make the extracted information available to subsequent business-process steps.

Typical uses include:

• Extracting text from scanned images
• Reading text from photographs
• Processing image-based documents
• Extracting text from a specific image region
• Capturing text for downstream workflow processing
• Storing image-extraction results
• Validating extracted image text
• Automating image-to-text processing

Usage:

The Get Text from Image step is typically used after a workflow receives or generates an image that contains text.

During execution:

1. Provide the image file path.
2. Optionally select an image region.
3. Execute the Get Text from Image step.
4. The image text is extracted.
5. The extracted text is stored in the configured workflow variable or global variable.
6. The percentage result is stored in its configured workflow variable or global variable.
7. Continue workflow processing through the True or False path.

A typical workflow might look like this:

Typical workflow scenarios include:

• Scanned document processing
• Image-based form processing
• Label or tag processing
• Photograph text extraction
• OCR-style business processes
• Image-content validation
• Automated data entry
• Image-based workflow routing

To use this step, you need to set up an Azure ML service in the FlowWright application. Go to the Status > Settings > Configuration page. Select the Azure ML category from the drop-down menu. Click here to learn more about the Azure ML and Cognitive Service subscription. 

A sample Azure ML configuration is provided here for reference. 

Example:

Let’s build and execute the “clsAzureMLGetTextDef” example. 

• Create a new process definition named “clsAzureMLGetTextDef” and open it in designer mode. 
• Drag a "clsAzureMLGetText" step to the canvas.
• Connect the dots between the “Start” and “clsAzureMLGetText” steps, as shown above. 
• Click the "clsAzureMLGetText" step to configure its "Required" properties. Provide a name for the step. Provide the image file path on the app server. Provide a variable or global reference to store the result text and the accuracy percentage. Then click the Save button. Note: Click the "AI Predict" button for the Copilot to add new process steps that match your process description. 
   

• Click the "clsAzureMLGetText" step to configure its "Optional" properties. Select the region name from the drop-down list. Click the Save button. 

• Note: For more information on image regions, please refer to the publication. 

Image Regions

• The image file path indicates where the image is stored on the server. The example image used is included below for reference. 

• Save the process definition, create a new instance, and run it. Render the process instance. Click the process step to view its properties. The step should extract text from an image, and store the result in “variable.ResultText” as configured. 

Tips:

• Ensure that the configured File path points to an accessible image before executing the step.
• Use Select region name when text extraction should be limited to a predefined image region.
• Store the extracted text in a workflow variable when it is needed by subsequent steps.
• Store the percentage result separately so that downstream workflow logic can use it as required.
• Validate the extracted text before using it for business-critical decisions.
• Use the False path to handle image-processing failures or unexpected input conditions.
• Test representative images and image regions before deploying the workflow to production.
• Use this step with file-processing, business-rule, database, notification, and reporting steps to build complete image-processing workflows.

Notes:

• The step belongs to the Azure Cognitive Services category. 
• Its display name is Get Text from image. 
• File path is required. 
• Select region name is optional. 
• Variable/Global to store the text is required. 
• Variable/Global to store the percentage is required. 
• The region property uses the ClsImageRegionsList data type. 
• The step provides True and False execution paths. 
• The XML does not define the exact meaning, range, or runtime format of the stored percentage value. Therefore, those details should be verified from the implementation or runtime behavior rather than assumed.

Get Text from Image vs. Get Text from Document:

Both Get Text from Image (clsAzureMLGetText) and Get Text from Document (clsAzureMLFormRecognizer) are Azure Cognitive Services steps that extract information from visual content. Their primary difference is the type and breadth of analysis they perform.

When to use each step:

Use Get Text from Image when the workflow primarily needs to read text from an image.

Typical examples include:

• Photographs containing text
• Scanned image content
• Labels
• Image-based text
• Specific regions of an image
• OCR-oriented workflows

The optional Select region name property is particularly useful when the workflow needs to focus on a predefined area of the image.

Use Get Text from Document when the workflow needs broader document understanding.

The Form Recognizer definition specifically describes extraction of:

• Text
• Key/value pairs
• Selection marks
• Tables
• Document structure

This makes it better suited to structured forms and business documents than a step focused on image text extraction.

Key distinction:

The simplest way to distinguish the two is:

Get Text from Image: “Extract text from this image, optionally using a selected region.”

Get Text from Document: “Analyze this document and extract its text and structured information.”

The Get Text from Image XML explicitly defines the image file path, optional region selection, text output, and percentage output.

The Form Recognizer definition describes a broader document-analysis capability covering text, key/value pairs, selection marks, tables, and structure. Thus, the choice should be based on whether the workflow needs focused image-text extraction or broader document information extraction.

Definition Sample:

You may download the sample workflow definition from the link provided and import it into your FlowWright environment.

Note: Verify and complete any missing configuration after importing the sample, including:

• File path
• Optional region selection
• Variable/Global to store the text
• Variable/Global to store the percentage
• Success and failure workflow branches
• Any downstream processing that consumes the extracted values

After verifying the configuration, save and publish the workflow before execution.

Click here to download the sample file.